Queen Mary's College, Chennai

The recent advances in Multimodal AI & Generative AI open doors to the possibilities of solving key challenges for Persons with Learning Disability. To assist individuals facing difficulty in visual or auditory perception, this paper designs & develops a multimodal AI agent using recent advances in the field. We aim to solve the challenge of enabling persons with Visual or Auditory Processing Disorders to learn & communicate. We do this by exploring a design that allows the transformation of information across visual and language modalities. This design can be realized with the recent advances in Generative Multimodal AI. Based on each individual's needs, the AI agent dynamically adapts the Human Computer interaction model. For instance, for a child with Visual Processing Disorder (VPD), given the child's hindered ability to make sense of information taken in through the eyes, the Multimodal AI agent transforms any visual information into auditory user interaction. In another instance, for a person with Central Auditory Processing Disorder (CAPD), given the hindrance in the individual's ability to analyze information taken in through the ears, the AI dynamically translates any speech modality into visual cues. Thus the AI agent adapts dynamically to the strengths and abilities of the individual. To enable students with VPD to learn, the design allows the student to ask questions about an image. This design is realized as a Visual Question Answering task in Vision Language Transformer models. We explore interactive multimodal conversations with Few shot Learning and In-Context Instruction Tuning of Multimodal Large Language Models to address difficulty in visual reasoning. To enable persons with CAPD to learn, the design translates audio lectures into visual cues. This visual cue consists of a combination of words using speech recognition and Large Language Models based re-phrasing to simpler words, cross-modal retrieval of images to address auditory memory challenges, and AI-generated images. To identify the strengths of each child, we also explore Multimodal embedding based Multimodal latent space arithmetic to link AI across senses. To effectively integrate the proposed design into the mainstream, we explore a universal design based inclusive approach to extend the use case to create AI assistants for assisting children with different learning styles such as visual learners or auditory learners. To enable future research on the proposed design, we explore an architecture to compose a pipeline of AI models, and to connect with external systems via plugin connectors. We implement lab scale prototypes of this design and present a demo on the project webpage at https://sites.google.com/view/multimodallearningdisability.

Plants are documented in the pharmacological manufacturing on their extensive essential diversity by fine such as their broad range of pharmacological activities. The biologically dynamic compounds existing in plants are named phytochemicals or plant secondary metabolites. The screening, isolation, and characterization of phytochemicals involve a multidisciplinary approach, involving knowledge from various scientific fields. Screening involves identifying plant species or parts rich in specific bioactive compounds, using methods like ethnobotanical surveys, traditional knowledge, and literature review. Isolation techniques, such as maceration, Soxhlet extraction, supercritical fluid extraction, and microwave-assisted extraction, are used to separate phytochemicals from complex plant matrices. Chromatographic techniques are used to determine the chemical composition and structural characteristics of isolated compounds. This review deals with the collection of plants, the extraction of dynamic mixtures as of the plant-based materials and its phytochemical screening by qualitative and quantitative analysis methods.

Abstract The wound healing potentials of brown algae Turbinaria conoides aqueous extract (TCAe) and silver nanoparticles synthesized utilizing T. conoides aqueous extract (TCAgNPs) were investigated in this study. TCAgNPs and TCAe were tested for cytotoxicity on human dermal fibroblast cells using the 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide (MTT) assay, which revealed that TCAgNPs and TCAe were not cytotoxic and may be tested for medicinal qualities. TCAgNPs and TCAe were tested for wound healing efficacy using a wound scratch assay on human dermal fibroblast cells. The damaged cells were subjected to TCAgNPs and TCAe, which demonstrated stronger wound repair activities than the control (Untreated). The cell cycle study of human dermal fibroblast primary cell lines treated with TCAgNPs and TCAe, as well as those not treated, was performed using flow cytometry to determine the DNA content of the nuclei. These findings show that TCAgNPs-treated cells proliferated more than TCAe and control-treated cells, implying that cell proliferation is boosted, which aids the wound-healing process. During immunoblot analysis, the TCAgNPs-treated group showed higher collagen and fibronectin expression than the TCAe-treated group. Our findings imply that TCAgNPs and TCAe can repair wounds in vitro and could be used as a source of wound healing agents.

PurposeThis research formulated to obtain the optimum ordered quantity and optimum inventory range of fish products under the conditions: (1) fully back ordered (lockdown) and (2) partial back ordered (normal geographical market). In both the cases, due to the deterioration nature and in quarantine situation some vendors are not able to satisfy the customers (retailers). So in this model, the cost of penalty is introduced in quarantine time to obtain the optimal total cost.Design/methodology/approachTo find the total cost, holding cost, shortage cost and deterioration cost have to be considered. There are so many disadvantages in holding the deteriorating food products. Due to the demand and deterioration, the holding cost of the fish products is determined. The supply chain of fish marketing process to find the optimum total cost and optimum back ordered quantity in the two situations, namely, (1) normal backordering and (2) Quarantine period is explained.FindingsThe conclusion of this research is exhibited for the uncertain lockdown situation and the normal geographical markets. But in both the cases, the demand function is dependent on the backorder quantity. The expected total cost of the retailers of fish products increased at the least possible range with the increase in the shortage parameter, cost of penalty and variance. But the change in mean value leads to decreasing in the back ordered quantity, inventory level and the annual total cost of the retailers. This analysis contributes to the service of supply chain from wholesaler to retailer in high level.Research limitations/implicationsFish products are very essential for nourishment and economic spread in India. This study has spotlight the efficient method for reducing the total cost of the retailers of fish marketing. The cost of deterioration of fish is high because of its perishable nature. Due to lockdown situation, the holding cost of the fish products depends upon the backordered quantity of geographical market of fish.Practical implicationsThis research formulated to obtain the optimum ordered quantity and optimum inventory range of fish products under the conditions: (1) fully back ordered (lockdown) and (2) partial back ordered (normal geographical market).Social implicationsDue to lockdown situation, the holding cost of the fish products depends upon the backordered quantity of geographical market of fish. This research formulated to obtain the optimum ordered quantity and optimum inventory range of fish products.Originality/valueThis research formulated to obtain the optimum ordered quantity and optimum inventory range of fish products under the conditions: (1) fully back ordered (lockdown) and (2) partial back ordered (normal geographical market). In both the cases, due to the deterioration nature and in quarantine situation some vendors are not able to satisfy the customers (retailers). So in this model, the cost of penalty is introduced in quarantine time to obtain the optimal total cost. A few number of sensitivity analysis are carried out for deterioration rate, shortage parameter and cost of penalty to indicate the existence of total cost in the least possible range.

A good ecosystem is necessary for a good and thriving society. The procedure has indeed been susceptible to bad errors and negligence due to the age-old practice of employing people to frequently inspect and clear loaded garbage cans. Furthermore, due to differing regularity of trash can use across regions, time-based regular inspections are unproductive since a trashcan may be overflowing quickly and require quick care, or there may be without the need for a normal inspection for a longer period. As a result, spilling, and smelling trash cans become even more of an issue than a fix, making the current system resource costly and ineffective. The current proposal is to construct Smart Trash cans with NodeMCU that analyse and transmit data to the ThingSpeak IoT platform, which incorporates a deep learning model which classifies trash based on if it is compostable or not and whether or not the trash can is overflowing. It also features a graphical user interface that indicates the level of trash in the bin.